Maximilian Müller f20db76f54 Add device tensor documentation for GPU execution providers (#20837) ... This documentation adds documentation on: - how to allocate CUDA device tensors from C++ and python - how to use DML device tensors from C++ and python - it also shows how to leverage existing GPU allocations in ORT - how to overlap PCI copies and GPU execution using CUDA streams - how to overlap PCI copies and GPU execution using D3D12 Command Lists and custom resources --------- Co-authored-by: Tianlei Wu <tlwu@microsoft.com>		2024-06-12 09:11:25 -07:00
..
model-optimizations	Update quantization.md for QDQ and dynamic quantization old doc (#20130)	2024-04-04 21:38:20 -07:00
tune-performance	Add device tensor documentation for GPU execution providers (#20837)	2024-06-12 09:11:25 -07:00
device-tensor.md	Add device tensor documentation for GPU execution providers (#20837)	2024-06-12 09:11:25 -07:00
index.md	Added initial ORT Extensions docs for onnxruntime website (#16723)	2023-09-01 15:56:33 -07:00
mobile-performance-tuning.md	[Docs] Update performance sections (#15071)	2023-03-17 15:39:22 -07:00
olive.md	Add On Device Training Tutorial with ONNX Runtime (#16167)	2023-06-15 16:01:26 -07:00
transformers-optimization.md	update docs for a new cuda provider option: enable_skip_layer_norm_strict_mode (#15770)	2023-05-02 17:54:59 -07:00